2 Commits

Author	SHA1	Message	Date
lintsinghua	31dc476015	feat: Improve streaming LLM token usage reporting by adding input estimation, requesting usage via `stream_options`, and providing fallback estimation.	2025-12-12 16:30:57 +08:00
lintsinghua	f05c0073e1	feat(agent): implement comprehensive agent architecture with knowledge base and persistence layer ... - Add database migrations for agent checkpoints and tree node tracking - Implement core agent execution framework with executor, state management, and message handling - Create knowledge base system with framework-specific modules (Django, FastAPI, Flask, Express, React, Supabase) - Add vulnerability knowledge modules covering authentication, cryptography, injection, XSS, XXE, SSRF, path traversal, deserialization, and race conditions - Introduce new agent tools: thinking tool, reporting tool, and agent-specific utilities - Implement LLM memory compression and prompt caching for improved performance - Add agent registry and persistence layer for checkpoint management - Refactor agent implementations (analysis, recon, verification, orchestrator) with enhanced capabilities - Remove legacy agent implementations (analysis_v2, react_agent) - Update API endpoints for agent task creation and project management - Add frontend components for agent task creation and enhanced audit UI - Consolidate agent service architecture with improved separation of concerns - This refactoring provides a scalable foundation for multi-agent collaboration with knowledge-driven decision making and state persistence	2025-12-12 15:27:12 +08:00